Suzan Ece Ada

Postdoctoral researcher @ETHZürich / Boğaziçi CMPE / Robert College

[Suzan Ece Ada @suzaneceada]

🚨 NeurIPS Spotlight 🚨 #NeurIPS2025

How can we handle non-Markovian time-evolving offsets at test time in Offline Reinforcement Learning?
Tired of retraining and hyperparameter optimization when a new non-stationary pattern arises?

Introducing FORL: Forecasting in Non-stationary Offline RL

Towards real-world non-stationarity: We bridge the gap between offline RL and forecasting. 👇
📍San Diego Convention Center Exhibit Hall C,D,E #202
📅 11:00-14:00, Fri, Dec 5
📄 Forecasting in Offline Reinforcement Learning for
Non-stationary Environments https://t.co/z29G0bdDyC
🌐 https://t.co/pZKApiyRd7

Why is this important?
✨ LLMs: Semantic/contextual bias.
💊📈 Healthcare & Finance: Data may be withheld (privacy/regulations).
🦾 Industrial Robots: Sensors drift, requiring daily calibration.

FORL unifies:
1️⃣ Conditional Diffusion Models: Generate candidate states conditioned on action-effect (Δo, a) history.
2️⃣ Zero-shot Forecasting: Uses time-series foundation models.
3️⃣ Dimension-wise Closest Match: A lightweight approach to fuse information from both sources (no hyperparameters & no fallback mechanism)

How can an agent infer its location when the state is subject to large unknown offsets?
This action-effect (Δo, a) history is invariant to the offset. We train the diffusion model to generate plausible states conditioned on this history.

✅ No need to retrain when new patterns arise.
✅ Bypasses tedious hyperparameter optimization.
✅ Trained only on standard offline RL datasets.

We validated FORL on a novel benchmark integrating widely used time-series data and offline RL datasets on:
✅ No access to past offsets
✅ Inter/intra-episode drifts
✅ Policy-agnostic plug-and-play
✅ Offset magnitude-scaling

Suzan Ece Ada @suzaneceada, Georg Martius @GMartius, Emre Ugur @emreugur__, Erhan Oztop @ErhanOztop
🎥 https://t.co/WOlbEUyOHp
#NeurIPS #NeurIPS2025 #ReinforcementLearning #OfflineRL #DiffusionModels

[Suzan Ece Ada @suzaneceada]

@behzatrasuli @emreugur__ @UniBogazici @alperahmetoglu @iamyigyil Çok teşekkür ederim Behzat Hocam 🙏❤️☺️

[Boğaziçi Üni. Bilgisayar Mühendisliği Bölümü @Bogazici_CmpE]

@colorsLab_boun üyesi olan Dr. Suzan Ece Ada, doktorasını Emre Uğur @emreugur_ danışmanlığında ve Erhan Öztop eş-danışmanlığında yürütmüş olup doktora sonrası araştırmalarına ETH Zürich’te devam etmektedir. Mezunumuzu ve hocalarımızı çok tebrik ederiz 🎉

[Boğaziçi Üni. Bilgisayar Mühendisliği Bölümü @Bogazici_CmpE]

Dr. Ada’nın “Robust and Adaptive Deep Reinforcement Learning” başlıklı doktora tezi, Boğaziçi Üniversitesi Bilimsel Araştırma Projeleri Komisyonu tarafından üstün bilimsel niteliğe sahip olması nedeniyle Doktora Tez Ödülü’nü almaya layık görülmüştür.

[Boğaziçi Üni. Bilgisayar Mühendisliği Bölümü @Bogazici_CmpE]

Doktora mezunumuz Dr. Suzan Ece Ada @suzaneceada BAP Doktora Tez Ödülü’nü aldı 🏆

[Suzan Ece Ada @suzaneceada]

@emreugur__ @Bogazici_CmpE @colors_lab_boun Çok teşekkür ederim Emre Hocam!☺️

[Suzan Ece Ada @suzaneceada]

I’m presenting FORL!

📍San Diego Convention Center Exhibit Hall C,D,E #202
📅 11:00-14:00, Fri, Dec 5
📄 Forecasting in Offline Reinforcement Learning for
Non-stationary Environments https://t.co/OOFDfBYW8I
🌐 https://t.co/iyFbM1uLbp…

[Suzan Ece Ada @suzaneceada]

🚨 NeurIPS Spotlight 🚨 #NeurIPS2025

How can we handle non-Markovian time-evolving offsets at test time in Offline Reinforcement Learning?
Tired of retraining and hyperparameter optimization when a new non-stationary pattern arises?

Introducing FORL: Forecasting in Non-stationary Offline RL

Towards real-world non-stationarity: We bridge the gap between offline RL and forecasting. 👇
📍San Diego Convention Center Exhibit Hall C,D,E #202
📅 11:00-14:00, Fri, Dec 5
📄 Forecasting in Offline Reinforcement Learning for
Non-stationary Environments https://t.co/z29G0bdDyC
🌐 https://t.co/pZKApiyRd7

Why is this important?
✨ LLMs: Semantic/contextual bias.
💊📈 Healthcare & Finance: Data may be withheld (privacy/regulations).
🦾 Industrial Robots: Sensors drift, requiring daily calibration.

FORL unifies:
1️⃣ Conditional Diffusion Models: Generate candidate states conditioned on action-effect (Δo, a) history.
2️⃣ Zero-shot Forecasting: Uses time-series foundation models.
3️⃣ Dimension-wise Closest Match: A lightweight approach to fuse information from both sources (no hyperparameters & no fallback mechanism)

How can an agent infer its location when the state is subject to large unknown offsets?
This action-effect (Δo, a) history is invariant to the offset. We train the diffusion model to generate plausible states conditioned on this history.

✅ No need to retrain when new patterns arise.
✅ Bypasses tedious hyperparameter optimization.
✅ Trained only on standard offline RL datasets.

We validated FORL on a novel benchmark integrating widely used time-series data and offline RL datasets on:
✅ No access to past offsets
✅ Inter/intra-episode drifts
✅ Policy-agnostic plug-and-play
✅ Offset magnitude-scaling

Suzan Ece Ada @suzaneceada, Georg Martius @GMartius, Emre Ugur @emreugur__, Erhan Oztop @ErhanOztop
🎥 https://t.co/WOlbEUyOHp
#NeurIPS #NeurIPS2025 #ReinforcementLearning #OfflineRL #DiffusionModels

[bigAI @BrownBigAI]

Why does most of hierarchical RL stop at the first layer of hierarchy—i.e. skills? Because until now, it wasn't clear how to learn the state abstractions in a principled way! Our recent NeurIPS paper shows how to start with a set of skills and learn state abstractions. 🧵1/8

[Suzan Ece Ada @suzaneceada]

@tuna_tugcu @emreugur__ @colors_lab_boun @Bogazici_CmpE Çok teşekkür ederim Tuna Hocam 🙏

[Suzan Ece Ada @suzaneceada]

@emreugur__ @colors_lab_boun @Bogazici_CmpE Sizinle ve Erhan hocamla çalışmak büyük bir ayrıcalıktı, çok teşekkür ederim hocam! Değerli jüri üyelerim, İnci Baytaş, Arzucan Özgür, Fatma Güney, Özgür Öğüz hocalarıma da çok teşekkür ederim 🙏🙏

[Emre Ugur @emreugur__]

@colors_lab_boun @Bogazici_CmpE öğrencim Suzan Ece Ada başarılı bir sunum ile doktorasını almaya hak kazandı. Robotica dergisi ile başladığı yayınlarını, 2 IEEE RA-L ve 1 Access makalesi ekledikten sonra NeurIPS Spotlight 🥳 ile en ileri noktaya taşıdı. Çok tebrikler Dr. Ada!

[Suzan Ece Ada @suzaneceada]

@radke149 Same

[Georg Martius @GMartius]

@svlevine was just presenting in the Exploration in AI @ #ICML2025 and promoted that exploration needs to be grounded, and that VLMs are a good source ;-) Check our paper below
👇

[Thomas Rupf @th_rupf]

Zero-shot imitation from just a single sparse demonstration is hard. Goal-conditioned methods tend to “greedily" move from one state to the next and lose the big picture.

We're presenting an alternative approach on Tuesday at #ICML2025.

(1/3)

[Marco Bagatella @mar_baga]

When multiple tasks need improvements, fine-tuning a generalist policy becomes tricky. How do we allocate a demonstration budget across a set of tasks of varied difficulty and familiarity?

We are presenting a possible solution at ICML on Wednesday!

(1/3)

[Cansu Sancaktar @CcansuSancaktar]

✨Introducing SENSEI✨ We bring semantically meaningful exploration to model-based RL using VLMs.

With intrinsic rewards for novel yet useful behaviors, SENSEI showcases strong exploration in MiniHack, Pokémon Red & Robodesk.

Accepted at ICML 2025🎉
Joint work with @cgumbsch
🧵

[Tom Silver @tomssilver]

We have an awesome line-up of speakers:

Chelsea Finn (@chelseabfinn)
David Hsu (@NUSComputing, tentative)
George Konidaris (@BrownBigAI)
Emre Ugur (@emreugur__)
Danfei Xu (@danfei_xu)

[myolab.ai @MyolabAI]

All forms of intelligence co-emerged with a body, except AI

We're building a #future where AI evolves as your lifelike digital twin to assist your needs across health, sports, daily life, creativity, & beyond...

https://t.co/QL3o9YxZYz ➡️ Preview your first #HumanEmbodiedAI

[Emre Ugur @emreugur__]

@suzaneceada is presenting at the moment.